MARN - AAAI18

Code for Multi-attention Recurrent Network - AAAI 2018

Dependencies / Notes

MARN is written in pytorch with some code fragments (1. LSTM Hybrid and 2. Multi Attention Head) copied from CMU-Multimodal SDK https://github.com/A2Zadeh/CMU-MultimodalSDK/.

• The code is developed with Python 3.6 and Pytorch 1.2.0 (with GPU support) on Linux
• For reasons of my convenience data is required to be data_dir = ../../data -- errors might pop-up when other directories are used.
• The model can be executed by running MARN.py.

Please contact Sunny Verma at firstname.lastname@uts.edu.au for reporting bug fixes or suggestions.